Search Results for author: Dohyun Kim

Found 8 papers, 1 papers with code

Deep ensemble network with explicit complementary model for accuracy-balanced classification

no code implementations10 Aug 2019 Dohyun Kim, Kyeorye Lee, Jiyeon Kim, Junseok Kwon, Joongheon Kim

The average accuracy is one of major evaluation metrics for classification systems, while the accuracy deviation is another important performance metric used to evaluate various deep neural networks.

Classification General Classification

TMA: Tera-MACs/W Neural Hardware Inference Accelerator with a Multiplier-less Massive Parallel Processor

no code implementations8 Sep 2019 Hyunbin Park, Dohyun Kim, Shiho Kim

The key figure of merit in hardware inference accelerators is the number of multiply-and-accumulation operations per watt (MACs/W), where, the state-of-the-arts MACs/W remains several hundreds Giga-MACs/W.

Distributed, Parallel, and Cluster Computing Hardware Architecture Signal Processing

Self-Driving like a Human driver instead of a Robocar: Personalized comfortable driving experience for autonomous vehicles

no code implementations12 Jan 2020 Il Bae, Jaeyoung Moon, Junekyo Jhung, Ho Suk, Taewoo Kim, Hyungbin Park, Jaekwang Cha, Jinhyuk Kim, Dohyun Kim, Shiho Kim

Moreover, we propose a vehicle controller based on control parameters enabling integrated lateral and longitudinal control via preference-aware maneuvering of autonomous vehicles.

Autonomous Vehicles

Handling Out-Of-Vocabulary Problem in Hangeul Word Embeddings

no code implementations EACL 2021 Ohjoon Kwon, Dohyun Kim, Soo-Ryeon Lee, Junyoung Choi, SangKeun Lee

Word embedding is considered an essential factor in improving the performance of various Natural Language Processing (NLP) models.

Word Embeddings

Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning

no code implementations26 Sep 2022 Hyunjae Lee, Gihyeon Lee, Junhwan Kim, Sungjun Cho, Dohyun Kim, Donggeun Yoo

However, it often results in selecting a sub-optimal configuration as training with the high-performing configuration typically converges slowly in an early phase.

Image Classification Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.